Fork me on GitHub

I'm in the middle of moving to the Computer Vision Group at NASA - JPL. I will be working on RGB-D related perception problems for 3D mapping, mobile manipulation, outdoor SLAM etc. Quite a lot of exciting projects means expect more updates soon!

What are the spatial representations, computer vision algorithms, and object search strategies needed to visually localize objects in large environments?

In this regard, I have come up with four main contributions that each spawned a project on its own:

Learning 3D context of everyday objects from Kinect images
What can we learn from 38,000 rooms?
Active visual search in Unexplored Large Environments
Kinect@Home: Crowdsourcing in the wild Kinect images
News
a Kinect@Home 3D model!
Research Interests
  • Active Visual Search
  • Semantic Mapping
  • Machine Learning